© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98091
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anson
    -0.28
    ç®´
    -0.25
    _MATRIX
    -0.25
    alus
    -0.25
    æĪĸå°Ĩ
    -0.25
    .Broadcast
    -0.25
    å±ĬæŶ
    -0.25
    onica
    -0.25
    owa
    -0.24
    achu
    -0.24
    POSITIVE LOGITS
    æ¤į被
    0.28
    æĬ½çĥŁ
    0.27
    æīģ
    0.26
    UG
    0.26
    æĻ¶
    0.26
    æ°ĶåĢĻåıĺåĮĸ
    0.25
     messing
    0.25
    åį´è¢«
    0.25
    ä¸ĸ
    0.24
    æģ¯
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.